Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 20756
    Prev
    Next
    INDEX
    Explanations

    the concept of starting or building something from the very beginning or from basic materials

    oai_token-act-pair · gpt-3.5-turbo

    references to starting or creating things from the ground up

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CVE
    -0.78
    agonist
    -0.75
    amide
    -0.68
    ossession
    -0.68
    rid
    -0.66
    odka
    -0.64
    ombs
    -0.63
    AAF
    -0.63
     conflic
    -0.62
    quickShipAvailable
    -0.62
    POSITIVE LOGITS
     scratch
    0.97
    pad
    0.93
     scratched
    0.91
    manship
    0.90
    eting
    0.83
    ratch
    0.83
    beat
    0.81
    brush
    0.77
    bones
    0.76
    pell
    0.76
    Activations Density 0.032%

    No Known Activations